Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add vadimcomanescu/codex-skills --skill information-architectgit clone --depth 1 https://github.com/vadimcomanescu/codex-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/vadimcomanescu/codex-skills/information-architect)<a href="https://agentmods.dev/skills/vadimcomanescu/codex-skills/information-architect"><img src="https://agentmods.dev/badge/skills/vadimcomanescu/codex-skills/information-architect.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00077 | $0.01779 |
| Opus 5 | $0.00039 | $0.00890 |
| Sonnet 5 | $0.00015 | $0.00356 |
| Haiku 4.5 | $0.00008 | $0.00178 |
Grade A, and why
information-architect scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Information Architect
Make complex products feel simple by giving users a consistent mental model: clear hierarchy, stable navigation, predictable labels, and strong wayfinding.
This skill is for designing the structure (what goes where and why). Pair with frontend-design when you also need a UI/visual redesign.
Quick Start (do this first)
- Ask up to 5 questions:
- Who are the primary users and their top 3 jobs-to-be-done (and what must feel “easy”)?
- What surface is this (web app, marketing site, docs/KB, mobile app)? Any SEO, i18n, or accessibility constraints?
- What exists today (current nav/sitemap), what’s broken, and what must not change?
- What are the “things” in the system (entities/content types) and what are the “actions” users do to/with them?
- Any hard constraints: permissions/roles, compliance, product strategy, roadmap, or analytics targets?
- Choose one primary organizing principle (one “north star”):
- task-first, object-first, lifecycle-based, audience-based, or frequency-based (see
references/ia-models-and-principles.md)
- Produce the minimum set of IA artifacts (in this order):
- IA thesis (1–2 sentences): the organizing logic + how users will find things
- Map: sitemap/app map (
SITEMAP.mmd; template inassets/ia-docs/) - Navigation spec: global + local + contextual nav rules (
NAVIGATION.md; template inassets/ia-docs/) - Labeling & naming rules: consistent labels, verbs/nouns, capitalization (
references/labeling-and-microcopy.md) - Taxonomy/metadata (only if needed): tags/facets + ownership rules (
TAXONOMY.csv; template inassets/ia-docs/)
Guardrails (utmost simplicity)
- Prefer fewer, clearer choices over “complete” categorization. Users scan; they don’t read.
- Keep top-level navigation small and stable. If everything is top-level, nothing is.
- Don’t mix organizing principles at the same level (e.g., “By Team” next to “Settings” next to “Reports”).
- Avoid duplicate pathways unless the user benefit is explicit (and labeled consistently).
- Use progressive disclosure: reveal complexity when it becomes relevant; keep early steps lightweight.
- Names are UX: labels must match user language, not org structure or internal terminology.
- Optimize for wayfinding: users should always know where they are, what’s here, and what’s next.
- When in doubt, scan
references/anti-patterns.mdand delete complexity.
What ships with it
15 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/ia-docs/CONTENT_INVENTORY.csv 190 B
- assets/ia-docs/CONTENT_MODEL.md 557 B
- assets/ia-docs/DECISIONS.md 305 B
- assets/ia-docs/IA.md 845 B
- assets/ia-docs/NAVIGATION.md 1.2 KB
- assets/ia-docs/SITEMAP.mmd 524 B
- assets/ia-docs/TAXONOMY.csv 230 B
- LICENSE.txt 1.0 KB
- references/anti-patterns.md 1.3 KB
- references/ia-models-and-principles.md 5.7 KB
- references/labeling-and-microcopy.md 2.6 KB
- references/migration-and-governance.md 1.5 KB
- references/research-and-validation.md 2.3 KB
- references/search-and-filters.md 1.9 KB
- scripts/scaffold_ia_docs.py 1.6 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 126 lines · 77 tokens per session scan A 128f4515e36f
information-architect is a skill published in the GitHub repository vadimcomanescu/codex-skills (24 stars, last pushed 7mo ago), licensed MIT. It adds 77 tokens to every session and 1,779 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.